© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36928
    Prev
    Next
    INDEX
    Explanations

    periodically, Dell, descriptive

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining why and how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ∝
    0.50
     stalks
    0.46
     ঋণ
    0.46
    の中から
    0.44
    ඵ
    0.44
     قرض
    0.44
     ঊ
    0.44
     toneladas
    0.43
     externalities
    0.43
     overdraft
    0.43
    POSITIVE LOGITS
     descrizione
    0.45
     Descriptive
    0.42
    <0xD7>
    0.42
    issime
    0.41
    acariy
    0.41
    itatif
    0.41
     Și
    0.41
    ર્ટ
    0.41
     Neues
    0.40
     Beschreibung
    0.40
    Activations Density 0.000%

    No Known Activations